#!/usr/bin/env python
# coding: utf-8
#
#
#
# Gaussian Naive Bayes ile Iris Veriseti Sınıflandırması
#
# In[1]:
import matplotlib.pyplot as plt
import numpy as np
from IPython.display import Image,HTML
from sklearn import datasets
iris = datasets.load_iris()
HTML("""""")
# In[2]:
Image(filename="C:\\Users\\ceakn\\Desktop\\1-site-resimler\\iris.png")
# In[3]:
print(iris.feature_names)
# In[4]:
print(iris.target_names)
# In[5]:
iris.data
# In[6]:
print(iris.target)
# In[7]:
print(type(iris.data))
print(type(iris.target))
print(type(iris))
print(iris.data.shape)
# In[8]:
np.isnan(iris.data).any()
np.isnan(iris.target).any()
# In[9]:
X = iris.data
y = iris.target
#
#
# Gerekli Kütüphanenin İçe Aktarılması
#
# In[10]:
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
# In[11]:
classifier.fit(X,y)
#
#
# Eğitim ve Test Kümelerine Ayırma (Train/Test split)
#
# In[12]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=4)
# In[13]:
print(X_train.shape ,X_test.shape)
# In[14]:
print(y_train.shape ,y_test.shape)
# In[15]:
y_pred = classifier.predict(X_test)
# Hata Oranını Bulalım
# In[16]:
from sklearn.metrics import accuracy_score
# In[17]:
print(accuracy_score(y_test, y_pred))
# In[18]:
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
cm
# 1 hatalı sonucumuz varmış